Event Recap: Race, Socioeconomic Factors, & Misinformation in Disease Outcomes and Public Health
COVID-19 has disproportionately impacted communities of color, and the spread of health misinformation online has influenced health services and behaviors. Boston University researchers are using artificial intelligence (AI) to determine how biases and misinformation affect health and healthcare.
Researchers in the Leveraging AI to Examine Disparities and Bias in Health Care Focused Research Program held their second workshop Race, Socioeconomic Factors, and Misinformation in Disease Outcomes and Public Health on Thursday May 27, 2021. Faculty and staff from engineering, communications, public health, and more came together to discuss methods for equitable predictive health modeling and the impacts of social media health misinformation on society.
Yannis Paschalidis, Professor in Electrical & Computer Engineering, Systems Engineering, Biomedical Engineering and Faculty of Computing & Data Sciences, discussed “The racial and socioeconomic signature of severe COVID-19 disease”. Paschalidis is using data from a social determinants of health screener for primary care patients at Boston Medical Center to create calculators that predict COVID-19 related intubations and ICU transfers. The calculators could help public health officials identify serious COVID-19 surges and take actions that prevent hospitals from reaching capacity.
Yang Hu, a PhD Candidate in Electrical & Computer Engineering, discussed, “Race and social determinants of health factors in hypertension”. Hu is studying how race and social determinants of health affect the control of hypertension, or high blood pressure. Hu has found that there are significant disparities between Black patients and white patients in how social needs impact hypertension.
Yiyan Zhang, a PhD Candidate in Emerging Media Studies, discussed, “Who calls it the “Chinese virus” and then what? The cross-platform partisan framing about China’s role in the COVID-19 pandemic among US news media and the health impacts”. Zhang is studying how publishing platforms influence partisan framing in digital news. Zhang found that conservative websites and Twitter accounts tend to adopt more sensational frameworks compared to liberal websites and Twitter accounts, with the partisan being the most extreme on Twitter compared to news websites. Now, Zhang is examining how selective, partisan news consumption affects people’s belief in China-related conspiracy theories and stigmatization.
Nina Cesare, a Postdoctoral Associate in the School of Public Health, discussed, “Understanding Population Health via Digital Data: Foundations, challenges and applications”. Cesare studies population health through social media, and found that there are significant associations between the number of tweets that talk about masking and actual mask usage. Twitter’s time and location sensitive data could provide public health officials with important details on a community’s attitudes towards health services and their behaviors.
This Focused Research Program’s symposium is scheduled for Monday October 18, 2021. Make sure to sign up for our newsletter to get information on how to register!